template-academic-pipeline
Research-to-publication orchestrator for template projects: research, write, verify, review, revise, reproduce, validate, and finalize. USE WHEN the user wants the whole paper workflow or enters midstream with an existing paper or reviewer comments.
Best use case
template-academic-pipeline is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Research-to-publication orchestrator for template projects: research, write, verify, review, revise, reproduce, validate, and finalize. USE WHEN the user wants the whole paper workflow or enters midstream with an existing paper or reviewer comments.
Teams using template-academic-pipeline should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/academic-pipeline/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How template-academic-pipeline Compares
| Feature / Agent | template-academic-pipeline | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Research-to-publication orchestrator for template projects: research, write, verify, review, revise, reproduce, validate, and finalize. USE WHEN the user wants the whole paper workflow or enters midstream with an existing paper or reviewer comments.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Academic pipeline Template-native orchestrator for the full research-to-publication path. It coordinates existing skills and file-backed controls; it does not introduce an autonomous hidden approval loop. ## Natural invoke - "Run the complete research-to-paper workflow" - "I already have a paper; review and finalize it" - "I received reviewer comments; revise and verify" - "Prepare this manuscript for Zenodo or arXiv" ## Inputs to confirm - **Entry point** - new research, existing paper, reviewer comments, or finalization. - **Project** - active template project or private project path; preserve confidentiality boundaries. - **HITL mode** - full-auto, gate-only, checkpoint, or project policy from pipeline control. - **Required gates** - claim verification, reproducibility, validation, review, and publication package checks. ## Workflow 1. **Stage map** - research -> paper plan/draft -> claim verification -> read-only review -> revision -> re-review -> reproducibility -> validation -> final package. 2. **Material passport** - record handoffs as file paths and generated artifacts: search corpus, claim ledger, evidence registry, artifact manifest, snapshots, validation reports, and reviewer matrices. 3. **Human checkpoints** - use existing HITL controls for gate-only or checkpoint approvals; detached review files live under `output/hitl/`. 4. **Integrity gates** - run claim verification before review and finalization; run double-run reproducibility before release claims. 5. **Finalize** - render from source, validate outputs, copy deliverables, and document residual risks. Never hand-edit `output/` as the fix. ## Deliverables - Pipeline status table: stage, owner skill, inputs, outputs, gate, and next action. - Material passport summary with artifact paths and verification status. - Review and revision traceability matrix. - Final readiness report with claim, reproducibility, validation, and publication checks. ## Verification commands ```bash uv run python scripts/execute_pipeline.py --project <project> --core-only uv run python -m infrastructure.validation.cli evidence projects/<project> --fail-on-issues uv run python -m infrastructure.validation.cli integrity output/<project>/ uv run python -m infrastructure.core.pipeline.snapshot compare <left> <right> --output-dir projects/<project>/output ``` ## References - [MODE_REGISTRY.md](../MODE_REGISTRY.md) - [deep-research](../deep-research/SKILL.md) - [academic-paper](../academic-paper/SKILL.md) - [academic-paper-reviewer](../academic-paper-reviewer/SKILL.md) - [reproducibility-audit](../reproducibility-audit/SKILL.md)